This workshop will cover basic methodological concepts in causality like the potential outcomes model and directed acyclic graphs, as these are the most common modalities used by contemporary statisticians, econometricians, and social scientists more generally. It will cover, in detail, canonical research designs like regression discontinuity, instrumental variables, difference-in-differences, synthetic control. The workshop will also include group assignments in programming. The workshop follows Scott Cunningham’s book “Causal Inference: The Mixtape.”
Causal inference is a practice which attempts to determine whether given two events, one event caused the other. It is commonly used in program evaluation as well as research aimed to evaluate the empirical content of certain scientific theories such as estimates of the price elasticity of demand and returns to schooling. This class is meant to be a primer and so will cover the potential outcomes model, directed acyclic graphs, regression discontinuity, instrumental variables, difference in differences, synthetic control, and matching. It will be accompanied by efforts to introduce students to basic practices in programming as well as good research practices more generally.
Aims of the class:
- To help students become more familiar with the field of causal inference
- To empower students to apply research designs more competently to their own research
- To direct students towards better programming practices so that they are better able to perform quantitative forms of research
The registration fee is $50 and open to ARIA Members only; however, Non-Members may join ARIA to participate in the workshop. To join ARIA, click here. Members renewing or joining now, will be considered members through the 2022 calendar year.